WO2021075018A1

WO2021075018A1 - Information processing method

Info

Publication number: WO2021075018A1
Application number: PCT/JP2019/040833
Authority: WO
Inventors: 勇気小阪; 久保　雅洋; 利憲細井
Original assignee: 日本電気株式会社
Priority date: 2019-10-17
Filing date: 2019-10-17
Publication date: 2021-04-22
Also published as: JPWO2021075018A1; JP7367767B2

Abstract

This information processing device 100 comprises: a calculation unit 121) that calculates, on the basis of subject information, a schedule menu showing a menu for scheduled rehabilitation to be performed by the subject; and a control unit 122 that performs a control so as to display and output the schedule menu so that the schedule menu can be revised on an information processing terminal operated by a practitioner who is implementing the rehabilitation of the subject.

Description

Information processing method

The present invention relates to an information processing method, an information processing device, and a program.

Injuries, illnesses, old age, etc. may reduce movement and cognitive functions in daily life. In such cases, rehabilitation is performed at a rehabilitation facility in order to restore movement and cognitive function in daily life. In a rehabilitation facility, it is necessary to grasp the state of motor / cognitive function related to activities of daily living of the patient performing rehabilitation, and as an example of an index for measuring the state of such a patient, FIM (Functional Independence Measure: daily life) An index for measuring motor / cognitive function related to movement) is used. For example, as shown in Patent Document 1, the FIM is composed of a total of 18 items such as 13 types of exercise items and 5 types of cognitive items, and each item is evaluated to the extent that assistance of 4 stages or 7 stages is required. I'm supposed to do it.

Then, in the rehabilitation facility, in order to effectively rehabilitate the patient, the rehabilitation menu is decided according to the patient's situation. At this time, the patient rehabilitation menu is determined according to the patient data such as the contents of the rehabilitation performed by the patient in the past, the evaluation value of each item of the FIM, and the characteristics of the patient. Especially in recent years, in order to enable quick and effective rehabilitation, we automatically present candidates for rehabilitation menus using models learned using past patient data, and make decisions based on those candidates. It is considered to do. It takes time to select the optimal rehabilitation menu for each patient's condition from a large number of menu types, but by narrowing down the menu candidates using the learning model, the optimal rehabilitation menu can be selected in a short time. There is an effect that can be determined.

On the other hand, as described above, when a candidate for a rehabilitation menu is automatically presented and the candidate is referred to, a menu that is not always effective for the patient may be presented. In such a case, the therapist selects the most suitable rehabilitation menu for each patient's condition from a large number of menu types, and it can be said that there is no effect of using the learning model described above.

Here, if there is no effect of using the learning model as described above, it is necessary to further perform additional learning of the model. In this case, the therapist asks, for example, that there was no optimal rehabilitation menu for the patient among the candidates using the model, and what was the actual rehabilitation menu selected (what was the optimal rehabilitation menu for the patient). Input that to the system to perform additional training of the model. As a result, it is possible to output a candidate for a rehabilitation menu that is more suitable for the patient to the same patient next time by using the additionally learned model.

More specifically, the timing for outputting the rehabilitation menu candidates that are more suitable for the patient is when the therapist decides the patient's rehabilitation menu. Therefore, each time the therapist decides on a patient's rehabilitation menu, it is desirable that there is an optimal rehabilitation menu for the patient among the candidates using the model. On the other hand, when the therapist decides the patient's rehabilitation menu, if there is no optimal rehabilitation menu for the patient among the candidates using the model, it means that there was no optimal rehabilitation menu and the rehabilitation menu actually selected. I want information about what was. Without that information, the next time the therapist decides on a patient's rehabilitation menu, it is likely that there is no optimal rehabilitation menu for the patient, diminishing the benefits of presenting rehabilitation menu candidates depending on the model.

As an example, patients are usually given rehabilitation time three times a day. Therefore, the same patient has an opportunity to present rehabilitation menu candidates using the model at least three times a day. Therefore, if there is no optimal rehabilitation menu for the patient among the candidates output by the model at the time of the first rehabilitation, there is a possibility that there is no optimal rehabilitation menu for the patient at the time of the second rehabilitation as well. high. Therefore, it is important for the model to input before the time of the second rehabilitation that there is no optimal rehabilitation menu for the patient among the candidates output by the model at the time of the first rehabilitation.

Japanese Unexamined Patent Publication No. 2017-0274776

For the above reasons, the therapist needs to input information about rehabilitation, but if the therapist is busy, it is difficult to do so even if he / she requests the input of such information.

Therefore, an object of the present invention is to propose an information processing method, an information processing device, and a program that can solve the above-mentioned problem that the therapist does not input information on rehabilitation.

The information processing method, which is one embodiment of the present invention, is
Based on the target person information, calculate the planned menu that represents the rehabilitation menu that the target person plans to perform,
The schedule menu is displayed and output so that it can be modified on the information processing terminal operated by the person who performs the rehabilitation of the target person.
It takes the configuration.

Further, the information processing device which is one embodiment of the present invention is
A calculation unit that calculates a planned menu that represents the rehabilitation menu that the target person plans to perform based on the target person information.
A control unit that controls the schedule menu to be displayed and output so that it can be modified by the information processing terminal operated by the person who performs the rehabilitation of the target person.
With,
It takes the configuration.

Further, the program which is one form of the present invention is
For information processing equipment
A calculation unit that calculates a planned menu that represents the rehabilitation menu that the target person plans to perform based on the target person information.
A control unit that controls the schedule menu to be displayed and output so that it can be modified by the information processing terminal operated by the person who performs the rehabilitation of the target person.
To realize,
It takes the configuration.

The present invention is configured as described above, and can prompt the rehabilitation practitioner to input information on rehabilitation.

It is a figure for demonstrating FIM. It is a figure which shows the whole structure of the information processing system in this invention. It is a block diagram which shows the structure of the data management apparatus disclosed in FIG. It is a figure which shows an example of the display screen displayed on the information processing terminal disclosed in FIG. It is a figure which shows an example of the display screen displayed on the information processing terminal disclosed in FIG. It is a flowchart which shows the operation of the information processing system disclosed in FIG. It is a block diagram which shows the hardware structure of the information processing apparatus in Embodiment 2 of this invention. It is a block diagram which shows the structure of the information processing apparatus in Embodiment 2 of this invention. It is a flowchart which shows the operation of the information processing apparatus in Embodiment 2 of this invention.

<Embodiment 1>
The first embodiment of the present invention will be described with reference to FIGS. 1 to 6. 1 to 5 are diagrams for explaining the configuration of the information processing system, and FIG. 6 is a diagram for explaining the processing operation of the information processing system.

[Constitution]
In the information processing system of the present embodiment, the therapist exercises in daily life for a patient (subject) whose motor and cognitive functions related to activities of daily living have deteriorated due to injury, illness, old age, or the like. It is used by the therapist to record the content of rehabilitation performed by such patients when performing rehabilitation in a rehabilitation facility for cognitive recovery.

Then, the therapist mentioned above decides the menu showing the contents of the patient's rehabilitation. For example, the therapist may use patient data stored in an electronic medical record, such as the above-mentioned "gender", "age group", "consciousness level (JCS: Japan Coma Scale)", "disease name", "paralyzed state", and " The therapist himself is in charge of referring to "evaluation value of each item of FIM (Functional Independence Measure) at each time point such as at the time of admission and after rehabilitation" and "rehabilitation implementation history (implementation date, implementation time, menu, etc.)". Determine the rehabilitation menu to improve the function of each item of FIM. The rehabilitation menu includes, for example, information on "training content" and "site". Examples of "training content" include "strength training", "range of motion training", "walking training", "training using orthoses", "work therapy", "cooking training", "life training", etc. is there. Examples of "parts" include "none", "right foot", "left foot", "right arm", "left arm", and "whole body".

Here, the FIM, which is an index for measuring the motor / cognitive function related to the activities of daily living of the patient, will be described with reference to FIG. As shown in FIG. 1, the FIM is composed of a total of 18 items, including 13 types of motor items for evaluating the patient's "motor function" and 5 types of cognitive items for evaluating the patient's "cognitive function". .. Specifically, FIM is an item for evaluating the movement function of the patient's "self-care" category as the above-mentioned exercise items, such as "meal", "conditioning", "bed bath", "changing clothes (upper body)", and "changing clothes (upper body)". "Lower body)", "toilet movement", "excretion control", "excretion control", which is an item to evaluate the movement function of the patient's "excretion" category, and "transfer" category, which is an item to evaluate the movement function of the patient. Includes items such as "bed / chair / wheelchair", "toilet", "tub / shower", and "walking / wheelchair", "stairs", which are items for evaluating the movement function of the patient's "movement" category. In addition, FIM is an item for evaluating the function of the patient's "communication" category as the above cognitive items, "understanding (auditory / visual)", "expression (voice / non-voice)", and patient's "social recognition". Includes items such as "social interaction," "problem solving," and "memory," which are items that evaluate the function of a category.

Then, in FIM, the degree of assistance required by the patient is evaluated on a 4-point or 7-point scale for each of the above-mentioned items. For example, as shown in the upper right column of FIG. 1, for each item, there are four levels such as "L1: complete assistance", "L2: with assistance", "L3: partial assistance", and "L4: independence". May be evaluated. For example, for each item, "1 point: total assistance", "2 points: maximum assistance", "3 points: moderate assistance", "4 points: minimum assistance", "5 points: monitoring", "6" In some cases, the degree of 7 levels is evaluated by points, such as "point: modified independence" and "7 points: complete independence". In the case of evaluating with a score of 7 stages in this way, the score may be totaled for each item, each category, and each function, and the patient may be evaluated.

The evaluation of each item of FIM described above is usually performed by a therapist (practitioner) who is an expert in performing patient rehabilitation. For example, the therapists are "occupational therapist (OP)", "physiotherapist (PT)", and "speech-language pathologist (ST)". However, the therapist is not limited to the above-mentioned person.

The evaluation value of each item of the FIM is input to the data management device 10 by the therapist described above, and is stored as patient data (subject information). For example, the data management device 10 stores patient data for each patient as an electronic medical record. In the electronic medical record, as patient data, for example, "gender", "age group", "consciousness level (JCS: Japan Coma Scale)", "disease name", "paralyzed state", "at the time of admission or after rehabilitation", etc. Information such as "evaluation value of each item of FIM at a time point" and "rehabilitation implementation history (implementation date, implementation time, menu, etc.)" is stored. However, the patient data is not necessarily limited to including the information of the above-mentioned contents, and may include only a part of the above-mentioned information, or may contain other information.

Then, in the present embodiment, the data management device 10 uses the patient data to calculate a scheduled menu representing the contents of the rehabilitation scheduled to be performed by the patient, and input the menu of the rehabilitation actually performed to the scheduled menu. It is configured as follows in order to realize that the therapist is encouraged to do so.

First, the data management device 10 is composed of one or a plurality of information processing devices including an arithmetic unit and a storage device. Then, as shown in FIG. 2, an information processing terminal 20 operated by the therapist T who performs rehabilitation for the patient U is connected to the data management device 10 via wireless communication. The information processing terminal 20 is composed of, for example, an information processing device such as a tablet terminal provided with a touch panel display, a smartphone, or a personal computer installed at a predetermined desk, and the type thereof is not particularly limited. The tablet terminal or smartphone, which is the information processing terminal 20, may be carried around by the therapist during work such as performing rehabilitation.

Then, as shown in FIG. 3, the data management device 10 includes a learning unit 11, a prediction unit 12, and a control unit 13 constructed by the arithmetic unit executing a program. Further, the data management device 10 includes a data storage unit 14 and a model storage unit 15 formed in the storage device. Hereinafter, each configuration will be described in detail.

The data storage unit 14 stores the electronic medical record for each patient U, and stores the patient data as described above. That is, the data storage unit 14 contains "basic information" such as "gender", "age group", "consciousness level", "disease name", and "paralyzed state" of each patient U, and "each item of FIM at each time point". It stores "rehabilitation information" such as "evaluation value" and "rehabilitation implementation history (implementation date, implementation time, menu, etc.)". As will be described later, the data storage unit 14 is scheduled to be performed by the patient, and stores the rehabilitation schedule menu calculated using the model in a storage area different from the electronic medical record.

The data storage unit 14 stores therapist information, which is information of each therapist who performs rehabilitation for the patient U. Here, the therapist information includes, for example, identification information that identifies the therapist and attribute information that represents the attributes of the therapist. The therapist's attribute information is, for example, information representing the degree of experience as a therapist, and, for example, is composed of information representing the attributes of "expert", "normal", and "newcomer" in descending order of experience. However, the therapist's attribute information may include information representing attributes other than the degree of experience. In addition, the degree of experience may be expressed in a format different from the above-mentioned example.

The model storage unit 15 stores a model for calculating a schedule menu representing the contents of the rehabilitation scheduled to be performed by the patient from the patient data. As will be described later, the model is created by performing machine learning in the learning unit 11 using the patient data stored in the data storage unit 14 as learning data. However, the model is not necessarily limited to being created by the learning unit 11, and may be created by another device or another method.

The learning unit 11 creates a model for calculating a scheduled menu representing a rehabilitation menu scheduled to be performed by a patient by performing machine learning using existing patient data as learning data. For example, the learning unit 11 includes "basic information" such as "gender", "age group", "consciousness level", "disease name", and "paralyzed state" in patient data, and "FIM at the time of admission or at a predetermined time point". "Rehabilitation information" such as "evaluation value of item" and "past rehabilitation implementation history" is used as an input value (explanatory variable), and the rehabilitation actually planned by the therapist and then performed by the patient according to the patient's condition. A model that uses the "execution menu" that represents the content as the output value (objective variable) is generated by machine learning. As a result, the generated model is configured to output the rehabilitation schedule menu to be performed by the patient, using the patient data as an input value.

Hereinafter, the model for calculating the scheduled menu representing the rehabilitation menu scheduled to be performed by the patient in the learning unit 11 in the present embodiment will be described in detail. In the present embodiment, the learning unit 11 describes "basic information" such as "gender", "age group", "consciousness level", "disease name", and "paralyzed state" in the patient data, and "at the time of admission" for each past patient. "Evaluation value of each item of FIM at a predetermined time point", "Evaluation value of each item of FIM at a predetermined time point", "History of rehabilitation menu performed on a patient before a predetermined time point", etc. Using the information of "information" and the pair of rehabilitation menus executed at the predetermined time point, the occurrence probability indicating which rehabilitation menu was implemented in what kind of "rehabilitation information" is learned. That is, the learning unit 11 calculates the conditional probability. Specifically, in the present embodiment, naive Bayes is used as an example for the probabilistic model.

The learning unit 11 calculates the following equations for each rehabilitation menu and uses _{P (X u} | Y _n ) and P _{as models so that the conditional probabilities P (Y n} | X _u ) can be calculated. Learn (Y _n ).

Here, X indicates M-dimensional rehabilitation information of the patient (where M is an integer of 1 or more), and in particular, X _u indicates M-dimensional rehabilitation information of a predetermined patient U. Further, each of the rehabilitation information M-dimensional patient and _{X_ i (1 ≦ i ≦ M} ), in particular, each of the M-dimensional rehabilitation information given patient U and X _u _ _i. Further, Y _n represents the n (1 ≦ n ≦ N) th rehabilitation menu. P (Y _n | X _u ) is a conditional probability indicating the probability of occurrence of the rehabilitation menu Y _n _{under the condition that X u} is obtained as the rehabilitation information of the patient. Here, it is assumed that there are N types of rehabilitation menus in total. And Y _n represents the nth kind of rehabilitation menu. P (X _u | Y _n ) is a conditional probability indicating the probability of occurrence _{of the rehabilitation information X u} of a predetermined patient U under the condition that the rehabilitation menu Y _{n is obtained.} P (X _u _ _i | Y _n ) is a conditional indicating the probability of occurrence _{of the rehabilitation information X u} _ _i of the predetermined patient U under the condition that _{the rehabilitation menu Y n} of the predetermined patient U is obtained. Probability. P (Y _n ) is the probability of occurrence of the rehabilitation menu Y _{n of a predetermined patient U.}

Further, the learning unit 11 performs the rehabilitation of the patient U as described later, and each time the actual execution menu of the rehabilitation is input, the learning unit 11 uses the patient data including the actual execution menu as the learning data to model. It also has the ability to learn to correct. The function of modifying the model by the learning unit 11 will be described later.

The prediction unit 12 calculates a rehabilitation schedule menu to be executed for a predetermined patient U using the model stored in the model storage unit 15. For example, the prediction unit 12 has "gender", "age group", "consciousness level", "disease name", "paralyzed state" among the patient data of the patient U who is scheduled to perform rehabilitation for the model. "Basic information", "evaluation value of each item of FIM at the time of admission or at a predetermined time", "rehabilitation information" such as "past rehabilitation implementation history" will be input, and the output value from the model will be executed. It will be the scheduled menu for rehabilitation. The prediction unit 12 may create a model for calculating the schedule menu by inputting only a part of the above-mentioned patient data into the model. Further, the prediction unit 12 is not necessarily limited to calculating the schedule menu using the model as described above, and may calculate the schedule menu by another method.

Specifically, the prediction unit 12 receives, for example, rehabilitation information X _u of a predetermined patient U, and
_{P (X u} _ _i | Y _n ) and P (Y _n ) are calculated using the model stored in the model storage unit 15. Then, for all the candidate rehabilitation menus, the conditional probability P (Y _n | X _u ) is calculated for each rehabilitation. Here, it is assumed that there are N types of rehabilitation menus in total. Then, the larger the conditional probability P (Y _n | X _u ), the more appropriate the rehabilitation menu for the predetermined patient U, and the scheduled menu is set.

The control unit 13 is set to display the schedule menu predicted by the prediction unit 12 on the electronic medical record of the patient U. However, the control unit 13 does not record the schedule menu on the electronic medical record, but stores the schedule menu in a storage area different from the electronic medical record in the data storage unit 14, and controls to display the schedule menu on the electronic medical record. .. Then, the control unit 13 outputs the schedule menu set on the electronic medical record of the patient U so as to be displayed on the display of the information processing terminal 20 operated by the therapist T. For example, when the therapist T requests the data of the predetermined patient U via the information processing terminal 20 before the therapist T rehabilitates the predetermined patient U, the control unit 13 causes the patient to the information processing terminal 20. Output to display the rehabilitation schedule menu that U executes. As an example, as shown in FIG. 4, the control unit 13 displays a “scheduled menu” on the display of the information processing terminal 20 as a “execution program” of the rehabilitation along with the “implementation time” and the “number of units”. "Content" and "Part" are displayed. In the example of FIG. 4, the "scheduled menu" is displayed as "training content: walking training" and "part: right foot".

Further, the control unit 13 displays and outputs to the information processing terminal 20 so that the therapist T can modify the scheduled menu (training content, part) on the information processing terminal 20. That is, the control unit 13 outputs the schedule menu so as to display the schedule menu on the display screen of the information processing terminal 20 such as a tablet terminal or a personal computer. Specifically, when the therapist T inputs a correction instruction to the displayed schedule menu, the information processing terminal 20 modifies the schedule menu into a correction menu in response to the correction instruction, and the correction menu Is notified to the control unit 13 of the data management device 10. In response to this, the control unit 13 modifies the schedule menu set on the electronic medical record of the patient U into a correction menu. That is, the control unit 13 stores the modified menu in which the scheduled menu is modified in the data storage unit 14, and modifies the display of the scheduled menu on the electronic medical record to the modified menu. As shown in FIG. 4, when the scheduled menu (training content, part) is displayed on the touch panel display of the information processing terminal 20, the therapist T displays the scheduled menu (training content: walking training, part:). By tapping (right foot), other menus (training content, part) that can be changed are displayed so that they can be selected, and the therapist T can select by tapping any menu (training content, part). The created menu is input as a modification menu instead of the schedule menu.

Note that the control unit 13 may display and output the schedule menu to the information processing terminal 20 so that it can be modified by another method. For example, as shown in FIG. 5, when the schedule menu (training content, part) is displayed on the touch panel display of the information processing terminal 20, the therapist T displays the schedule menu (training content: walking training, part:). By tapping the "Correction" button displayed under (right foot), other menus (training content, part) that can be changed are displayed so that they can be selected, and the therapist T can select any menu (training content, part). By tapping to select, the selected menu is entered as a modification menu instead of the appointment menu.

The control unit 13 may display the above-mentioned schedule menu of the patient U on the data management device 10 or another information processing device. Also in this case, similarly to the above, the schedule menu is displayed and output on the display of the data management device 10 or the like so that the schedule menu can be modified.

Further, when the control unit 13 receives an operation input from the therapist T to the information processing terminal 20 or the data management device 10 to confirm the rehabilitation menu to be performed, the control unit 13 displays the contents of the currently displayed menu. , Confirm as the execution menu to be actually executed and record it in the electronic medical record. At this time, if the schedule menu is not modified, the schedule menu becomes the execution menu, and if the schedule menu is modified to the modification menu, the modification menu becomes the execution menu. The therapist T, for example, presses the "confirm" button as shown in FIGS. 4 and 5, to input an operation to confirm the menu.

When the "scheduled menu" initially set on the electronic medical record is modified to the "correction menu" and recorded as the "execution menu", the control unit 13 has these "scheduled menu" and "execution menu". , And "identification information of the therapist who made the correction", and record it in the data storage unit 14 as a correction history.

Here, the learning unit 11 described above will be further described. The learning unit 11 further performs machine learning to modify the model based on the execution menu input as described above. Specifically, when the therapist T first confirms the schedule menu as the execution menu modified to the modification menu as described above, the learning unit 11 adds the patient data to the learning data and relearns the model. I do.

At this time, as described above, the learning unit 11 describes "basic information" such as "gender", "age group", "consciousness level", "disease name", and "paralyzed state" in the patient data for each past patient. Evaluation value of each item of FIM at the time of admission ”,“ Evaluation value of each item of FIM at a predetermined time point ”,“ History of rehabilitation menu performed on the patient before the predetermined time point ”, etc. The information of the "rehabilitation information" and the pair of the rehabilitation menu carried out at the predetermined time point is used as the first information. Then, regarding the patient U who performed the execution menu modified by the therapist T, "basic information" such as "gender", "age group", "consciousness level", "disease name", and "paralyzed state" in the patient data, Patient U's "evaluation value of each item of FIM at the time of admission", "evaluation value of each item of FIM before the time when the execution menu was executed with the scheduled menu modified from the therapist T to the correction menu", "therapist" The therapist uses the "rehabilitation information" of the "history of the rehabilitation menu performed on the patient" and the "execution menu modified by the therapist T" as paired information before the execution menu modified by T. The information of the pair of rehabilitation menus that T performed on patient U is used as the second information. Then, by using the second information in addition to the first information, the model is relearned by re-learning the probability of occurrence indicating which rehabilitation menu was implemented in what kind of "rehabilitation information". Fix it. That is, the learning unit 11 recalculates the conditional probability.

Note that the learning unit 11 may perform machine learning so as to weight the learning data and modify the model according to the attribute of the therapist T who modified the schedule menu into the execution menu. For example, as described above, the attribute information of the therapist T is information indicating the degree of experience as a therapist, and the attributes of "expert", "normal", and "newcomer" are set in descending order of experience. To do. It can be said that the higher the degree of experience of the therapist T, the higher the reliability of the therapist. Then, in this case, the higher the degree of experience, the more the number of the second information including the "execution menu" modified by the therapist is multiplied by the weight, and the model is modified. By increasing the number, the modified model has the effect of increasing the probability of occurrence of the "execution menu" modified by the therapist. Therefore, for example, in the case of "expert", the weight is set to 3.0, in the case of "normal", the weight is set to 2.0, in the case of "newcomer", the weight is set to 1.0, and so on. That is, the number of the second information including the "execution menu" modified by the "expert" therapist is 1, but this is increased from 1 to 3 to modify the model. By increasing the number from one to three, the modified model has the effect of increasing the probability of occurrence of the "execution menu" modified by the "expert" therapist.

As a result, a model that more reflects the knowledge of the therapist with a high degree of experience is generated, that is, a model is generated in which the execution menu modified by the therapist with a high degree of experience appears more frequently as a scheduled menu. Will be done.

Further, the learning unit 11 may generate a model for calculating the schedule menu for each therapist T. In this case, the learning unit 11 performs machine learning to generate a model for each therapist T by extracting patient data including an execution menu in which the schedule menu is modified for each therapist T and using it as learning data. As a result, a model that reflects the rehabilitation policy for each therapist T will be generated.

Further, even if the learning unit 11 uses the patient data including the modified schedule menu in the execution menu as the learning data, the learning unit 11 generates a model so that the frequency with which the modified schedule menu is calculated as an output value is reduced. Good. For example, the modified schedule menu may be learned so as not to be output as a stop word, or the weight of the modified schedule menu may be set to 0 for learning. At this time, the therapist's attributes may be reflected as described above. For example, the higher the experience of the therapist, the lower the weight of the scheduled menu modified by the therapist may be set and learned.

As described above, the learning unit 11 may increase the number of learning data as the degree of experience representing the attributes of the therapist is higher, and the number of learning data including the modified schedule menu is decreased and modified. The number of training data including the execution menu may be increased for training.

Further, the learning unit 11 may generate a model so as to calculate a schedule menu according to the attributes of the therapist performing the rehabilitation. In this case, first, the "therapist's attributes" are associated with the "training contents" and "parts" that make up the "scheduled menu". For example, the higher the experience of the therapist, the higher the risk of rehabilitation but the higher the effect, and the lower the experience, the lower the risk of rehabilitation but the lower the risk. Then, the learning unit 11 receives the input value including the "therapist's identification information" for performing the patient's rehabilitation, and the "scheduled menu" including the "training content" and the "site" corresponding to the "therapist's attribute". Generate a model with the output value of. By doing so, a model for calculating the schedule menu according to the degree of experience of the therapist is generated.

Here, the above-mentioned risk represents the risk of injury when the patient performs rehabilitation and the risk of functional deterioration due to rehabilitation. Therefore, if an inexperienced therapist implements a menu that increases the effect of rehabilitation but also increases the risk, the risk of performing rehabilitation increases and should be avoided. Therefore, it is important to output the schedule menu according to the degree of experience of the therapist.

[motion]
Next, the operations of the data management device 10 and the information processing terminal 20 constituting the above-mentioned information processing system will be described with reference to the flowchart of FIG. First, the data management device 10 acquires patient data of the patient U who is scheduled to perform rehabilitation (step S1). Then, the data management device 10 calculates a schedule menu representing the contents of the rehabilitation scheduled to be performed by the patient U based on the acquired patient data (step S2). For example, the data management device 10 has a “gender”, “age group”, “consciousness level”, and “disease name” among the patient data of the patient U for the model created in advance and stored in the model storage unit 15. , "Patient state" and other "basic information", "evaluation value of each item of FIM at the time of admission or at a predetermined time", "rehabilitation implementation history" and other "rehabilitation information" are input and calculated by the model. The output value is used as the scheduled menu to be executed in rehabilitation.

The data management device 10 acquires patient data of many patients U as learning data in advance, and in the patient data, "gender", "age group", "consciousness level", "disease name", " "Basic information" such as "paralyzed state", "evaluation value of each item of FIM at the time of admission or predetermined time", "rehabilitation information" such as "rehabilitation implementation history" are used as input values (explanatory variables) and actually executed. A model may be generated by machine learning in which the output value (objective variable) is the "execution menu" representing the contents of the rehabilitation.

Subsequently, the data management device 10 is set to display the schedule menu calculated as described above on the electronic medical record as the schedule menu for the rehabilitation scheduled to be executed by the patient U. Then, the data management device 10 outputs the schedule menu set in the electronic medical record of the patient U so as to be displayed on the display of the information processing terminal 20 operated by the therapist T who performs the rehabilitation of the patient U (step S3). As a result, the display of the information processing terminal 20 operated by the therapist T displays a schedule menu to be executed by the patient U, for example, as shown in FIGS. 4 and 5. The timing of displaying and outputting the schedule menu to the information processing terminal 20 is, for example, immediately before the scheduled start time of rehabilitation, immediately before the scheduled end time of rehabilitation, immediately after the scheduled end time of rehabilitation, and further from the therapist T. When there is a request, etc. can be considered. However, the timing of displaying the schedule menu is not limited to these.

After that, the therapist T confirms the rehabilitation schedule menu to be executed by the patient U displayed on the information processing terminal 20, browses the patient data which is other information of the patient U as necessary, and the therapist T. Determine the actual rehabilitation menu to be performed based on the knowledge and experience of the patient. Then, when the schedule menu displayed on the information processing terminal 20 is different from the determined menu, the therapist T operates the information processing terminal 20 to determine the displayed schedule menu, which is a correction menu. Modify to. Then, the information processing terminal 20 displays and outputs a correction menu instead of the schedule menu (step S4).

Then, when the therapist T completes the correction of the schedule menu displayed on the information processing terminal 20, for example, the confirmation process such as pressing the "confirm" button displayed on the information processing terminal 20 is performed, the correction is performed. The information processing terminal 20 notifies the data management device 10 of the information. When the data management device 10 receives the notification from the information processing terminal 20, the data management device 10 determines the input menu as the execution menu of the rehabilitation to be actually executed and records it in the electronic medical record (step S5). At this time, the data management device 10 records the "scheduled menu" before the correction, the "execution menu" after the correction, and the "identification information of the therapist" after the correction as the correction history in the data storage unit 14. deep.

After that, the data management device 10 is modified by the therapist T as described above, and further machine learning is performed so as to modify the model using the learning data including the execution menu recorded in the electronic medical record (step S6). At this time, the data management device 10 may modify the menu to a more appropriate model by changing the weight of the training data according to the attributes of the therapist who modified the menu or reducing the weight of the modified scheduled menu. it can. The modified model will be used later in calculating the rehabilitation schedule menu that patient U plans to perform.

As described above, according to the present embodiment, the schedule menu of the rehabilitation scheduled to be executed by the patient U is displayed on the information processing terminal 20 and the data management device 10 operated by the therapist T, and the schedule menu can be modified. I have to. This motivates the therapist T to confirm and correct the rehabilitation menu, prompts the therapist T to confirm and correct the rehabilitation menu, and suppresses omission of confirmation. It is possible to prompt the input of the menu carried out in. As a result, the rehabilitation menu performed by the patient U is appropriately recorded by the therapist T, and by referring to such a record, an appropriate rehabilitation menu candidate for the patient U can be output.

In addition, by changing the weight of the training data according to the therapist's attributes and the modified schedule menu and modifying the model that calculates the schedule menu, it is possible to improve the calculation accuracy of the schedule menu by the modified model. it can. Furthermore, it is possible to create a model for calculating the schedule menu for each therapist, and it is possible to create a model suitable for the therapist.

Also, in the above, the rehabilitation menu that improves the items set in the FIM is calculated. However, the data management device 10 and other devices described above may be used to calculate a rehabilitation menu that improves items set in other indicators such as evaluating the condition of the human body. For example, there is an index for evaluating activities of daily living, such as the "Barthel Index", which evaluates all 10 items set from the two viewpoints of personal movement and movement movement according to the degree of independence. A model for calculating a rehabilitation menu for the purpose of improving the above may be generated, and a scheduled menu may be calculated using such a model.

<Embodiment 2>
Next, a second embodiment of the present invention will be described with reference to FIGS. 7 to 9. 7 to 8 are block diagrams showing the configuration of the information processing apparatus according to the second embodiment, and FIG. 9 is a flowchart showing the operation of the information processing apparatus. In this embodiment, the outline of the configuration of the information processing system including the data management device 10 and the information processing terminal 20 described in the first embodiment and the information processing method by the information processing system is shown.

First, the hardware configuration of the information processing apparatus 100 according to the present embodiment will be described with reference to FIG. 7. The information processing device 100 is composed of a general information processing device, and is equipped with the following hardware configuration as an example.
-CPU (Central Processing Unit) 101 (arithmetic unit)
-ROM (Read Only Memory) 102 (storage device)
-RAM (Random Access Memory) 103 (storage device)
-Program group 104 loaded into RAM 303
A storage device 105 that stores the program group 304.
A drive device 106 that reads and writes the storage medium 110 external to the information processing device.
-Communication interface 107 that connects to the communication network 111 outside the information processing device
-I / O interface 108 for inputting / outputting data
-Bus 109 connecting each component

Then, the information processing apparatus 100 can construct and equip the calculation unit 121 and the control unit 122 shown in FIG. 8 by acquiring the program group 104 by the CPU 101 and executing the program group 104. The program group 104 is stored in, for example, a storage device 105 or a ROM 102 in advance, and the CPU 101 loads the program group 104 into the RAM 103 and executes the program group 104 as needed. Further, the program group 104 may be supplied to the CPU 101 via the communication network 111, or may be stored in the storage medium 110 in advance, and the drive device 106 may read the program and supply the program to the CPU 101. However, the calculation unit 121 and the control unit 122 described above may be constructed by an electronic circuit.

Note that FIG. 7 shows an example of the hardware configuration of the information processing device 100, and the hardware configuration of the information processing device is not limited to the above case. For example, the information processing device may be composed of a part of the above-described configuration, such as not having the drive device 106.

Then, the information processing device 100 executes the information processing method shown in the flowchart of FIG. 9 by the functions of the calculation unit 121 and the control unit 122 constructed by the program as described above.

As shown in FIG. 9, the information processing device 100 is
Based on the target person information, a schedule menu representing the schedule of rehabilitation scheduled to be performed by the target person is calculated (step S11).
The schedule menu is displayed and output so that it can be modified on the information processing terminal operated by the practitioner who performs the rehabilitation of the target person (step S12).

In the present embodiment, by being configured as described above, the schedule menu of the rehabilitation scheduled to be executed by the target person is displayed on the information processing terminal operated by the implementer, and in particular, the schedule menu can be modified. I have to. As a result, the practitioner can be urged to confirm or correct the rehabilitation menu, and omission of confirmation can be suppressed. As a result, the menu of rehabilitation performed by the subject is appropriately recorded by the practitioner, and by referring to such a record, appropriate rehabilitation contents for the subject can be planned.

Also in this embodiment, the evaluation value of the item set in the FIM is not limited to be used, and the value of the item set in another index for evaluating the state of the human body may be used. For example, there is an index for evaluating activities of daily living such as the "Barthel Index" that evaluates all 10 items set from the two viewpoints of personal movement and movement movement according to the degree of independence. May be used to calculate the schedule menu as described above.

<Additional notes>
Part or all of the above embodiments may also be described as in the appendix below. Hereinafter, the outline of the configuration of the information processing method, the information processing device, and the program in the present invention will be described. However, the present invention is not limited to the following configurations.

(Appendix 1)
Based on the target person information, calculate the planned menu that represents the rehabilitation menu that the target person plans to perform,
The schedule menu is displayed and output so that it can be modified on the information processing terminal operated by the person who performs the rehabilitation of the target person.
Information processing method.

(Appendix 2)
The information processing method described in Appendix 1
In response to an instruction from the implementer to modify the schedule menu displayed and output to the information processing terminal, the modification menu obtained by modifying the schedule menu is displayed and output to the information processing terminal, and the modification menu is displayed and output to the target. Record as an execution menu of rehabilitation performed by a person,

(Appendix 3)
The information processing method described in Appendix 2
Using the learning data consisting of the combination of the target person information and the execution menu, learning is performed to modify the model for calculating the scheduled menu from the target person information.
Information processing method.

(Appendix 4)
The information processing method described in Appendix 3
Learning to modify the model using learning data consisting of a combination of the target person information including the performer's information obtained by modifying the schedule menu into the modification menu and the execution menu.
Information processing method.

(Appendix 5)
The information processing method described in Appendix 4,
Learning to modify the model using the learning data consisting of a combination of the target person information and the execution menu so that the model differs according to the attribute of the implementer who modified the schedule menu to the modification menu. To do
Information processing method.

(Appendix 6)
The information processing method according to Appendix 4 or 5.
It is composed of a combination of the target person information and the execution menu so as to generate a model for calculating the schedule menu according to the degree of experience of performing the rehabilitation of the performer who modified the schedule menu to the modification menu. Learning to modify the model using the training data,
Information processing method.

(Appendix 7)
The information processing method according to any one of Supplementary note 4 to 6.
Learning to modify the model using the training data consisting of a combination of the execution menu and the target person information, which is obtained by modifying the schedule menu into the modification menu and giving weights according to the attributes of the implementer.
Information processing method.

(Appendix 8)
The information processing method according to any one of Appendix 3 to 7.
Using the learning data including the modified schedule menu, the model is generated so that the frequency with which the modified schedule menu is calculated is reduced.
Information processing method.

(Appendix 9)
The information processing method according to any one of Appendix 1 to 8.
Based on the subject information including the evaluation value representing the evaluation of the subject at a predetermined time in each of the plurality of items set in the FIM (Functional Independence Measure), the rehabilitation menu to be performed by the subject will be represented. Calculate the menu,
Information processing method.

(Appendix 10)
A calculation unit that calculates a planned menu that represents the rehabilitation menu that the target person plans to perform based on the target person information.
A control unit that controls the schedule menu to be displayed and output so that it can be modified by the information processing terminal operated by the person who performs the rehabilitation of the target person.
Information processing device equipped with.

(Appendix 11)
The information processing device according to Appendix 10.
The control unit controls the information processing terminal to display and output a modified menu obtained by modifying the scheduled menu in response to an instruction from the practitioner to modify the scheduled menu displayed and output to the information processing terminal. At the same time, the modification menu is controlled to be recorded as the execution menu of the rehabilitation performed by the target person.
Information processing device.

(Appendix 12)
The information processing device according to Appendix 11,
It is provided with a learning unit that learns to modify a model for calculating the scheduled menu from the target person information by using learning data composed of a combination of the target person information and the execution menu.
Information processing device.

(Appendix 13)
The information processing device according to Appendix 12,
The learning unit learns to modify the model by using learning data including a combination of the target person information including the information of the implementer who modified the scheduled menu into the modification menu and the execution menu.
Information processing device.

(Appendix 14)
The information processing device according to Appendix 13.
The learning unit uses the learning data composed of a combination of the target person information and the execution menu so that the model differs depending on the attribute of the implementer who has modified the scheduled menu into the modification menu. Learn to fix,
Information processing device.

(Appendix 15)
The information processing device according to

Appendix

13 or 14.
The learning unit modifies the scheduled menu to the modified menu, and the target person information and the execution menu are generated so as to generate a model for calculating the scheduled menu according to the degree of experience of performing the rehabilitation of the practitioner. Learning to modify the model using the training data consisting of a combination of
Information processing method.

(Appendix 16)
The information processing device according to any one of Appendix 13 to 15.
The learning unit modifies the model by using the learning data composed of a combination of the execution menu and the target person information, which is obtained by modifying the scheduled menu into the modification menu and giving weights according to the attributes of the implementer. Learn to do,
Information processing method.

(Appendix 17)
The information processing device according to any one of Appendix 13 to 16.
The learning unit uses the learning data including the modified schedule menu to generate the model so that the frequency with which the modified schedule menu is calculated is reduced.
Information processing device.

(Appendix 18)
For information processing equipment
A calculation unit that calculates a planned menu that represents the rehabilitation menu that the target person plans to perform based on the target person information.
A control unit that controls the schedule menu to be displayed and output so that it can be modified by the information processing terminal operated by the person who performs the rehabilitation of the target person.
A program to realize.

(Appendix 19)
The program described in Appendix 18
Further realized is a learning unit that learns to modify the model for calculating the scheduled menu from the target person information by using the learning data composed of the combination of the target person information and the execution menu in the information processing device. Program to let you.

(Appendix 1.1)
Based on the subject information including the evaluation value representing the evaluation of the subject at a predetermined time in each of the plurality of items set in the predetermined index for evaluating the condition of the human body, the rehabilitation menu scheduled to be performed by the subject is displayed. Calculate the planned menu to be represented,
The schedule menu is displayed and output so that it can be modified on the information processing terminal operated by the person who performs the rehabilitation of the target person.
Information processing method.

(Appendix 1.2)
The information processing method described in Appendix 1.1.
In response to an instruction from the implementer to modify the schedule menu displayed and output to the information processing terminal, the modification menu obtained by modifying the schedule menu is displayed and output to the information processing terminal, and the modification menu is displayed and output to the target. Record as an execution menu of rehabilitation performed by a person,
Information processing method.

(Appendix 1.3)
The information processing method described in Appendix 1.2.
Using the learning data consisting of the combination of the target person information and the execution menu, learning is performed to modify the model for calculating the scheduled menu from the target person information.
Information processing method.

The above-mentioned program can be stored and supplied to a computer using various types of non-transitory computer readable medium. Non-temporary computer-readable media include various types of tangible storage media. Examples of non-temporary computer-readable media include magnetic recording media (eg, flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (eg, magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, Includes CD-R / W, semiconductor memory (for example, mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (RandomAccessMemory)). The program may also be supplied to the computer by various types of temporary computer readable media. Examples of temporary computer-readable media include electrical, optical, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire and an optical fiber, or a wireless communication path.

Although the invention of the present application has been described above with reference to the above-described embodiment and the like, the present invention is not limited to the above-described embodiment. Various changes that can be understood by those skilled in the art can be made to the structure and details of the present invention within the scope of the present invention.

10 Data management device 11 Learning unit 12 Prediction unit 13 Control unit 14 Data storage unit 15 Model storage unit 20 Information processing terminal T Therapist U Patient 100 Information processing device 101 CPU
102 ROM
103 RAM
104 Program group 105 Storage device 106 Drive device 107 Communication interface 108 Input / output interface 109 Bus 110 Storage medium 111 Communication network 121 Calculation unit 122 Control unit

Claims

Based on the target person information, calculate the planned menu that represents the rehabilitation menu that the target person plans to perform,
The schedule menu is displayed and output so that it can be modified on the information processing terminal operated by the person who performs the rehabilitation of the target person.
Information processing method.
The information processing method according to claim 1.
In response to an instruction from the implementer to modify the schedule menu displayed and output to the information processing terminal, the modification menu obtained by modifying the schedule menu is displayed and output to the information processing terminal, and the modification menu is displayed and output to the target. Record as an execution menu of rehabilitation performed by a person,
Information processing method.
The information processing method according to claim 2.
Using the learning data consisting of the combination of the target person information and the execution menu, learning is performed to modify the model for calculating the scheduled menu from the target person information.
Information processing method.
The information processing method according to claim 3.
Learning to modify the model using learning data consisting of a combination of the target person information including the performer's information obtained by modifying the schedule menu into the modification menu and the execution menu.
Information processing method.
The information processing method according to claim 4.
Learning to modify the model using the learning data consisting of a combination of the target person information and the execution menu so that the model differs according to the attribute of the implementer who modified the schedule menu to the modification menu. To do
Information processing method.
The information processing method according to claim 4 or 5.
It is composed of a combination of the target person information and the execution menu so as to generate a model for calculating the schedule menu according to the degree of experience of performing the rehabilitation of the performer who modified the schedule menu to the modification menu. Learning to modify the model using the training data,
Information processing method.
The information processing method according to any one of claims 4 to 6.
Learning to modify the model using the training data consisting of a combination of the execution menu and the target person information, which is obtained by modifying the schedule menu into the modification menu and giving weights according to the attributes of the implementer.
Information processing method.
The information processing method according to any one of claims 3 to 7.
Using the learning data including the modified schedule menu, the model is generated so that the frequency with which the modified schedule menu is calculated is reduced.
Information processing method.
The information processing method according to any one of claims 1 to 8.
Based on the subject information including the evaluation value representing the evaluation of the subject at a predetermined time in each of the plurality of items set in the FIM (Functional Independence Measure), the rehabilitation menu to be performed by the subject will be represented. Calculate the menu,
Information processing method.
A calculation unit that calculates a planned menu that represents the rehabilitation menu that the target person plans to perform based on the target person information.
A control unit that controls the schedule menu to be displayed and output so that it can be modified by the information processing terminal operated by the person who performs the rehabilitation of the target person.
Information processing device equipped with.
The information processing device according to claim 10.
The control unit controls the information processing terminal to display and output a modified menu obtained by modifying the scheduled menu in response to an instruction from the practitioner to modify the scheduled menu displayed and output to the information processing terminal. At the same time, the modification menu is controlled to be recorded as the execution menu of the rehabilitation performed by the target person.
Information processing device.
The information processing device according to claim 11.
It is provided with a learning unit that learns to modify a model for calculating the scheduled menu from the target person information by using learning data composed of a combination of the target person information and the execution menu.
Information processing device.
The information processing device according to claim 12.
The learning unit learns to modify the model by using learning data including a combination of the target person information including the information of the implementer who modified the scheduled menu into the modification menu and the execution menu.
Information processing device.
The information processing apparatus according to claim 13.
The learning unit uses the learning data composed of a combination of the target person information and the execution menu so that the model differs depending on the attribute of the implementer who has modified the scheduled menu into the modification menu. Learn to fix,
Information processing device.
The information processing device according to claim 13 or 14.
The learning unit modifies the scheduled menu to the modified menu, and the target person information and the execution menu are generated so as to generate a model for calculating the scheduled menu according to the degree of experience of performing the rehabilitation of the practitioner. Learning to modify the model using the training data consisting of a combination of
Information processing method.
The information processing device according to any one of claims 13 to 15.
The learning unit modifies the model by using the learning data composed of a combination of the execution menu and the target person information, which is obtained by modifying the scheduled menu into the modification menu and giving weights according to the attributes of the implementer. Learn to do,
Information processing method.
The information processing device according to any one of claims 13 to 16.
The learning unit uses the learning data including the modified schedule menu to generate the model so that the frequency with which the modified schedule menu is calculated is reduced.
Information processing device.
For information processing equipment
A calculation unit that calculates a planned menu that represents the rehabilitation menu that the target person plans to perform based on the target person information.
A control unit that controls the schedule menu to be displayed and output so that it can be modified by the information processing terminal operated by the person who performs the rehabilitation of the target person.
A program to realize.
The program according to claim 18.
Further realized is a learning unit that learns to modify the model for calculating the scheduled menu from the target person information by using the learning data composed of the combination of the target person information and the execution menu in the information processing device. Program to let you.